Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

By Fengbin Zhu, Wenqiang Lei, Chao Wang, Jianming Zheng, Soujanya Poria, Tat-seng Chua. 2021

307 citations recorded by the source corpus.

Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents. Recently, there has been a surge in the amount of research literature on OpenQA, particularly on techniques that integrate with neural Machine Reading Comprehension (MRC). While these research works have advanced performance to new heights on benchmark datasets, they have been rarely covered in existing surveys on QA systems. In this work, we review the latest research trends in OpenQA, with particular attention to systems that incorporate neural MRC techniques. Specifically, we begin with revisiting the origin and development of OpenQA systems. We then introduce modern OpenQA architecture named"Retriever-Reader"and analyze the various systems that follow this architecture as well as the specific techniques adopted in each of the components. We then discuss key challenges to developing OpenQA systems and offer an analysis of benchmarks that are commonly used. We hope our work would enable researchers to be informed of the recent advancement and also the open challenges in OpenQA research, so as to stimulate further progress in this field.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

QuALITY: Question Answering with Long Input Texts, Yes! (2021, background): “While there are open-domain QA datasets that require longer contexts (Joshi et al., 2017; Zhu et al., 2021), the challenge is often ﬁnding the short excerpt that answers the questions at hand; however, long-document QA requires reading a long context and understanding it as a whole to correctly…”
A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT (2023, background): “These models can be used for a wide range of NLP tasks such as dialogue systems [58], , translation [59] and question answering [60].”
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance (2021, background): “Recently deep reasoning over textual data has gained increasing attention (Zhu et al., 2021), e.”
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions (2022, methodology): “To do this we follow a retrieve-and-read paradigm (Zhu et al., 2021), where the retriever first retrieves documents from the knowledge source and the QA model reads the retrieved documents and the question to generate the final answer.”
Knowledge Graph Prompting for Multi-Document Question Answering (2023, background): “…solution to overcome this limitation in conventional OD-QA and single document question-answering (D-QA) (Xu et al. 2020; Mathew, Karatzas, and Jawahar 2021) is to retrieve grounding contexts and derive faithful answers from the contexts, i.e., retrieve-and-read (Zhu et al. 2021; Ju et al. 2022).”
Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity (2024, background): “…the task of accurately answering a query by sourcing for query-relevant documents, and then interpreting them to provide answers (Chen et al., 2017; Zhu et al., 2021), which, thus, generally involves two modules: a retriever (Karpukhin et al., 2020; Xiong et al., 2021) and a reader (Yang et al.,…”
Generate rather than Retrieve: Large Language Models are Strong Context Generators (2022, methodology): “To evaluate the model performance, we use exact match (EM) score for evaluating open-domain QA (Zhu et al., 2021).”
Retrieval-Enhanced Machine Learning (2022, background): “Access to external knowledge, via knowledge grounding , may help with this issue [11, 22, 34, 39, 76].”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, unknown): “Besides CRSs, there are other conversational AI systems, e.g., task-oriented dialogue systems [23, 255, 151], social chatbots [128, 109, 228], conversational searching [205, 166, 163], and conversational question answering (QA) [270].”
Evaluation of Retrieval-Augmented Generation: A Survey (2024, methodology): “A.1 Retrieval Component The retrieval component of RAG systems in Figure 1 can be categorized into three types: sparse retrieval, dense retrieval [59], and web search engine.”
Exploiting Reasoning Chains for Multi-hop Science Question Answering (2021, methodology): “vector retriever has received increasing attention as it captures the semantic matching beyond simple word overlap and can be trained along with the reader (Zhu et al., 2021).”